Allow leading underscore in column name used in row filter (#1358)

* Update parser.py Allow leading underscore in column name used in row filter. * Update test_parser.py * Update test_parser.py * Update test_parser.py
apache · Nov 22, 2024 · d86ab6e · d86ab6e
1 parent 7a83695
commit d86ab6e
Show file tree

Hide file tree

Showing 2 changed files with 5 additions and 1 deletion.
diff --git a/pyiceberg/expressions/parser.py b/pyiceberg/expressions/parser.py
@@ -79,7 +79,7 @@
 NAN = CaselessKeyword("nan")
 LIKE = CaselessKeyword("like")
 
-unquoted_identifier = Word(alphas, alphanums + "_$")
+unquoted_identifier = Word(alphas + "_", alphanums + "_$")
 quoted_identifier = Suppress('"') + unquoted_identifier + Suppress('"')
 identifier = MatchFirst([unquoted_identifier, quoted_identifier]).set_results_name("identifier")
 column = DelimitedList(identifier, delim=".", combine=False).set_results_name("column")

diff --git a/tests/expressions/test_parser.py b/tests/expressions/test_parser.py
@@ -53,6 +53,10 @@ def test_quoted_column() -> None:
     assert EqualTo("foo", True) == parser.parse('"foo" = TRUE')
 
 
+def test_leading_underscore() -> None:
+    assert EqualTo("_foo", True) == parser.parse("_foo = true")
+
+
 def test_equals_true() -> None:
     assert EqualTo("foo", True) == parser.parse("foo = true")
     assert EqualTo("foo", True) == parser.parse("foo == TRUE")